Your Search FoundationSupercharged.
Our Customers
For Better Search
Our frontier models form the search foundation for high-quality enterprise search and RAG systems.
DeepSearch
Search, read and reason until best answer found.
Reader
Convert a URL to LLM-friendly input, by simply adding
r.jina.ai
in front.Embeddings
World-class multimodal multilingual embeddings.
Reranker
World-class neural retriever for maximizing search relevancy.
Classifier
Zero-shot and few-shot classification for image and text.
Segmenter
Cut long text into chunks and do tokenization.
Start instantly—no credit card or registration needed!
verified_user We are SOC 2 Type 1 & 2 compliant with the American Institute of Certified Public Accountants (AICPA).open_in_new
key
API Key & Billing
Reader
DeepSearch
Embeddings
Reranker
Classifier
Segmenter
chevron_leftchevron_right
globe_book
Use
r.jina.ai
to read a URL and fetch its contenttravel_explore
Use
s.jina.ai
to search the web and get SERPContent Format
You can control the level of detail in the response to prevent over-filtering. The default pipeline is optimized for most websites and LLM input.
Default
arrow_drop_down
JSON Response
The response will be in JSON format, containing the URL, title, content, and timestamp (if available). In Search mode, it returns a list of five entries, each following the described JSON structure.
Timeout
Maximum page load wait time, use this if you find default browser engine is too slow on simple webpage.
Token Budget
Limits the maximum number of tokens used for this request. Exceeding this limit will cause the request to fail.
Use ReaderLM-v2
Experimental
Uses ReaderLM-v2 for HTML to Markdown conversion, to deliver high-quality results for websites with complex structures and contents. Costs 3x tokens!
CSS Selector: Only
List of CSS selectors to target specific page elements.
body
.class
#id
CSS Selector: Wait-For
CSS selectors to wait for before returning results.
body
.class
#id
CSS Selector: Excluding
CSS selectors for elements to remove (headers, footers, etc.).
header
.class
#id
Remove All Images
Remove all images from the response.
Gather All Links At the End
A "Buttons & Links" section will be created at the end. This helps the downstream LLMs or web agents navigating the page or take further actions.
None
arrow_drop_down
Gather All Images At the End
An "Images" section will be created at the end. This gives the downstream LLMs an overview of all visuals on the page, which may improve reasoning.
None
arrow_drop_down
Forward Cookie
Our API server can forward your custom cookie settings when accessing the URL, which is useful for pages requiring extra authentication. Note that requests with cookies will not be cached.
<cookie-name>=<cookie-value>
<cookie-name-1>=<cookie-value>; domain=<cookie-1-domain>
Image Caption
Captions all images at the specified URL, adding 'Image [idx]: [caption]' as an alt tag for those without one. This allows downstream LLMs to interact with the images in activities such as reasoning and summarizing.
Use a Proxy Server
Our API server can utilize your proxy to access URLs, which is helpful for pages accessible only through specific proxies.
Use a Country-Specific Proxy Server
Set country code for location-based proxy server. Use 'auto' for optimal selection or 'none' to disable.
Bypass Cached Content
Our API caches URL contents for a certain amount of time. Set it to true to ignore the cached result and fetch the content from the URL directly.
Do Not Cache & Track!
When enabled, the requested URL won't be cached and tracked on our server.
Github Flavored Markdown
Opt in/out features from GFM (Github Flavored Markdown).
Enabled
arrow_drop_down
Stream Mode
Stream mode is beneficial for large target pages, allowing more time for the page to fully render. If standard mode results in incomplete content, consider using Stream mode.
Customize Browser Locale
Control the browser locale to render the page. Lots of websites serve different content based on the locale.
Strictly comply robots policy
Define bot User-Agent to check against robots.txt before fetching content.
iframe Extraction
Processes content from all embedded iframes in the DOM tree.
Shadow DOM Extraction
Extracts content from all Shadow DOM roots in the document.
Follow Redirect
Choose whether to resolve to the final destination URL after following all redirects. Enable to follow the full redirect chain.
Local PDF/HTML file
POST
Use Reader on your local PDF and HTML file by uploading them. Only support pdf and html files. For HTML, please also specify a reference URL for better parsing related CSS/JS scripts.
upload
Pre-run JavaScript
POST
Executes preprocessing JS code (inline string or remote URL).
Heading Style
Sets markdown heading format (passed to Turndown).
Number Sign Headings
arrow_drop_down
Horizontal Rule Style
Defines markdown horizontal rule format (passed to Turndown).
Bullet Point Style
Sets bullet list marker character (passed to Turndown).
*
arrow_drop_down
Emphasis Style
Defines markdown emphasis delimiter (passed to Turndown).
_
arrow_drop_down
Strong Emphasis Style
Sets markdown strong emphasis delimiter (passed to Turndown).
**
arrow_drop_down
Link Style
Determines markdown link format (passed to Turndown).
Inline
arrow_drop_down
EU Compliance
All infrastructure and data processing operations reside entirely within EU jurisdiction.
upload
Request
GET
Bash
Language
arrow_drop_down
curl https://r.jina.ai/https://example.com
key
API key
visibility_off
Available tokens
0
This is your unique key. Store it securely!
Our Publications
Understand how our frontier search models were trained from scratch, check out our latest publications. Meet our team at EMNLP, SIGIR, ICLR, NeurIPS, and ICML!
arXiv
March 04, 2025
ReaderLM-v2: Small Language Model for HTML to Markdown and JSON
arXiv
December 17, 2024
AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark
arXiv
December 12, 2024
jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images
ECIR 2025
September 18, 2024
jina-embeddings-v3: Multilingual Embeddings With Task LoRA
arXiv
September 07, 2024
Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models
EMNLP 2024
August 30, 2024
Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever
WWW 2025
June 21, 2024
Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models
ICML 2024
May 30, 2024
Jina CLIP: Your CLIP Model Is Also Your Text Retriever
arXiv
February 26, 2024
Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings
arXiv
October 30, 2023
Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents
EMNLP 2023
July 20, 2023
Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models
11 publications in total.